Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    mathematical or statistical calculations

    oai_token-act-pair · gemini-2.0-flash

    mathematical symbols

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     препратки
    -0.78
    horabuena
    -0.72
    StructEnd
    -0.69
    ImageContext
    -0.68
     Theſe
    -0.68
     Portail
    -0.67
    ScopeManager
    -0.65
     محفوظة
    -0.65
    Bakgrunnsstoff
    -0.65
    Skocz
    -0.63
    POSITIVE LOGITS
    #+#
    0.53
     Gilli
    0.45
    حياته
    0.44
    nasi
    0.43
     "..\..\..\
    0.42
    :+:
    0.40
    skjaer
    0.40
    괄
    0.39
    grine
    0.39
     Ke
    0.39
    Act Density 1.000%

    No Known Activations